Print
PDFMichael Callahan, a recent graduate of the systems and entrepreneurial engineering program at the University of Illinois at Urbana-Champaign (UIUC), recently received the prestigious Lemelson-Illinois Student Prize. The award recognizes Callahan for developing a device that will profoundly benefit people with amyotrophic lateral sclerosis (ALS, commonly known as Lou Gherig's disease), cerebral palsy, spinal cord injury, and other neurological disorders. The device, dubbed "The Audeo," acquires and translates neurological signals, so subjects who cannot speak or move can communicate. Callahan has teamed with Thomas Coleman and other UIUC colleagues to start their own company – Ambient Corporation – to develop and commercialize the technology. NI LabVIEW played a key role in creating the Audeo.
The Audeo is a sensory device placed around the neck of an afflicted person. In operation, it intercepts the signals from the brain that control the vocal chords and the vocal tract. These signals then are sent to a computer that filters out the noise from any background sources, processes it using a complex signal processing algorithm, and then interprets the person’s meaning from the signals to produce speech. The speech can then either be output directly or used to control external devices, such as a motorized wheelchair.
Figure 1. Michael Callahan (standing) teamed up with Thomas Coleman (seated) and other UIUC colleagues to develop a mind-computer interface that disabled people can use for thought-based control of their wheelchairs.
“People with ALS may be able to move their mouth a little, but they can’t exhale enough air from their lungs to produce audible speech. Since speech signals are produced by the brain even if they cannot speak, we can intercept those signals and create the speech for them,” says Coleman.
The team implemented prototypes, which use an application based on LabVIEW, to control the acquisition and apply signal processing that translates the nerve impulse signal samples into commands for speech or wheelchair control.
Figure 2. An application based on LabVIEW controls the acquisition and applies the signal processing that translates nerve impulse signal samples into commands for speech or wheelchair control.
To control a wheelchair, the system needs to identify directional commands: forward, right, left and stop. For it to do so, the software must identify those singular commands from the speech patterns, rather than process the data to produce continuous speech.
The continuous speech processing strategy that would allow the user to hear what they are producing as they are doing so is still in development.
“One of the challenges is to develop a universal mathematical transformation of the data that would work well for everyone - not just for a specific individual,” explained Callahan.
The job requires sophisticated signal processing algorithms that can adapt to nerve impulse patterns, which vary between individuals and over time. Using native LabVIEW graphical programming, Callahan and his team performed rapid trials using live signals with varying algorithms and parameters.
“LabVIEW simplifies development and encourages innovation by offering an intuitive graphical programming approach that allows you to focus on innovation rather than programming details," Callahan said.
He and his colleagues created the software with LabVIEW and built an initial prototype in 2005, and they continue to use LabVIEW throughout the development process. Callahan and Coleman have collected a large amount of data from numerous people and have developed a system around LabVIEW that can generate transformation algorithms and evaluate their effectiveness on the fly. Once the developers discover the optimum processing algorithms and fix the specific design parameters of the system, they will commit the entire acquisition and processing into hardware that will be contained in Audeo device itself. That way, there will be no need for an external computer in the system.
Figure 3. Using native LabVIEW aided the design process by enabling rapid trials using live signals with varying algorithms and parameters.
The result, they say, will not just be one device, but a range of devices that will target the needs of many different users. One such device, for example, might simply be dedicated to speech production, while another might be used by a disabled person to control a variety of different devices, such as a wheelchair, computer, or even a mobile phone.
Reader Comments | Submit a comment »
good product, poor choice of company name
Fantastic concept and product. They
may want to reconsider their company
name. Ambient Corporation was
organized in 1996 as a Delaware
corporation and went public in 1998
(OTC BB: ABPG), and is a Broadband
over Power Lines (BPL) provider.
- Oct 2, 2007
Legal
This material is protected under the copyright laws of the U.S. and other countries and any uses not in conformity with the copyright laws are prohibited, including but not limited to reproduction, DOWNLOADING, duplication, adaptation and transmission or broadcast by any media, devices or processes.